Tulsi Kumar Gupta

Data Scientist

Gurugram, Haryana, India4 yrs 11 mos experience

Most Likely To SwitchHighly Stable

Key Highlights

5+ years of experience in scalable ML solutions
Expert in end-to-end ML pipelines using AWS
Passionate about solving real-world problems

Stackforce AI infers this person is a Data Scientist specializing in E-commerce and Travel industries with strong machine learning capabilities.

Contact

tulasi15081997@gmail.com LinkedIn

Skills

Core Skills

Machine LearningData Science

Other Skills

AWS SageMakerML pipelinesLightGBMXGBoostdata analyticsDatabricksDeep LearningLogistic RegressionRandom Forestdata analysistorch serveBiomedical NEROCRweb scrapingRetrieval-Augmented Generation (RAG)

About

Data Scientist with 5+ years of experience building scalable ML solutions for pricing, recommendation, and demand optimization across large-scale data systems. Experienced in developing end-to-end ML pipelines using AWS SageMaker and PySpark, leveraging ensemble models and multi-source data (sales, clickstream, pricing, inventory) to drive measurable business impact. Passionate about building production-grade ML systems and solving real-world problems. Open to connecting and discussing opportunities in data science and machine learning.

Experience

4 yrs 11 mos

Total Experience

1 yr 7 mos

Average Tenure

3 yrs 3 mos

Current Experience

Adidas

Data Scientist

Feb 2023 – Present · 3 yrs 3 mos · Gurugram, Haryana, India

Built a scalable dynamic pricing system on AWS SageMaker using end-to-end ML pipelines to optimize pricing and discount strategies across markets and channels.
Developed a reusable ML submodule (pricekit) for feature engineering, training, and inference, leveraging a stacking ensemble (LightGBM, XGBoost, meta-learner) to generate price elasticity predictions and enable stock-constrained markdown optimization.
Designed a self-service analytics pipeline on Databricks to identify similar, complementary, and top-performing articles, supporting planners and traders in optimizing markdown strategies and detecting cannibalization.
Built a deep learning–based demand size curve model to improve inventory planning across e-commerce, retail, and wholesale channels using historical sales and demand patterns.

AWS SageMakerML pipelinesLightGBMXGBoostdata analyticsMachine Learning+1

Makemytrip

Data Scientist

Jun 2022 – Feb 2023 · 8 mos · Gurugram, Haryana, India

Developed propensity-to-buy models using Logistic Regression and tree-based models
(XGBoost and Random Forest) by engineering aggregated behavioral features like
sessions, booking time, user, and activities to identify high-intent users and improve
conversion across funnel stages and business lines.
Built a flight ranking model to recommend optimal flights based on user preferences
and key features, and analyzed hotel search data to generate insights on user behavior,
filter preferences, and booking patterns across markets.

Logistic RegressionXGBoostRandom Forestdata analysisMachine LearningData Science

Innoplexus

Associate Data Scientist

Jun 2021 – Jun 2022 · 1 yr · Pune, Maharashtra, India

• Worked on multiple language translation and create a torch serve translation API, Structured clinical trial data from NCBI database for multiple variables using a hybrid system of heuristic and Biomedical NER models for entities namely drug, gene, protein, disease, and, Create a model to generate the Novel Molecules on 3CLpro protein, OCR, web scrapping and pdf extraction.

torch serveBiomedical NEROCRweb scrapingMachine Learning